Kehua Su
9 papers · 2023–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(23)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Machine Learning
(7)
Core Methods
(5)
Artificial Intelligence
(4)
Deep Learning
(4)
Core AI
(4)
Learning Types · Machine Learning
(4)
Learning Types · Deep Learning
(3)
Interdisciplinary
(2)
Natural Language Processing
(2)
Application Areas
(2)
Architectures
(2)
Social
(2)
Applications
(1)
Learning Paradigms · Artificial Intelligence
(1)
Learning Paradigms · Machine Learning
(1)
Keywords
emotional reasoning
(2)
multimodal large language model
(2)
federated learning
(2)
knowledge distillation
(2)
feature interaction
(1)
multimodal learning
(1)
self-attention mechanism
(1)
class imbalance
(1)
density estimation
(1)
mutual information
(1)
protein representation
(1)
semantic similarity
(1)
language model
(1)
personalized model
(1)
supervised fine-tuning
(1)
mixture of expert
(1)
deep clustering
(1)
non-iid data
(1)
protein language model
(1)
binary classification
(1)
Papers
EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models
CVPR 2026
Anatomy-Conserving Unpaired CBCT-to-CT Translation via Schrödinger Bridge
MICCAI 2025
Catch Your Emotion: Sharpening Emotion Perception in Multimodal Large Language Models
ICML 2025
EMOE: Modality-Specific Enhanced Dynamic Emotion Experts
CVPR 2025
MMSite: A Multi-modal Framework for the Identification of Active Sites in Proteins
NeurIPS 2024
Dual Mutual Information Constraints for Discriminative Clustering
AAAI 2023
FedABC: Targeting Fair Competition in Personalized Federated Learning
AAAI 2023
Fine-Grained Position Helps Memorizing More, a Novel Music Compound Transformer Model with Feature Interaction Fusion
AAAI 2023
Improving Heterogeneous Model Reuse by Density Estimation
IJCAI 2023